1
Show HN: Betula Fuzzy Search
一个轻量级模糊搜索工具，支持快速模糊匹配，适合文本查找和自动化场景。
Article URL: https://gist.github.com/overflowy/9b6d30c7b65dd23c8899636595d88227 Comments URL: https://news.ycombinator.com/item?id=48924943 Points: 1 …
2
Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
用张量列低秩分解攻克扩散模型高维采样难题，带来理论与计算效率双重飞跃。
arXiv:2607.06841v1 Announce Type: cross Abstract: Diffusion models offer a powerful framework for sampling from complex probability densities by learn…
3
InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost
只需4B参数模型，就能实现前沿KOL搜索的语义匹配，大幅降低成本而不牺牲精度。
arXiv:2607.05968v1 Announce Type: cross Abstract: Matching influencers (KOLs) to free-form, multi-part Thai marketing criteria is today served either …
4
Reflected Schr\"odinger Bridge Matching
反射边界条件下Schrödinger桥匹配新方法，拓展最优传输理论在约束域的应用。
arXiv:2607.03626v1 Announce Type: new Abstract: Recent advances in generative modeling have enabled the efficient computation of Schr\"odinger bridges…
5
Matching AI Modality To User Intent: Designing The Right Interface
AI交互设计的核心：根据用户意图选择最合适的模态，打造无缝界面体验。
We’ve fallen into conversational tunnel vision, defaulting every AI capability into a chat-based interface simply because LLMs are trained on dialogue…
6
ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping
ShopX用基础模型打通购物意图到商品匹配，Agent电商新范式！
arXiv:2606.31693v1 Announce Type: cross Abstract: The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward in…
7
Why Choosing an AI Coding Tool Is Hard (And How to Pick the Right One)
选AI编程工具如选战友，工作流匹配远比功能数量重要，一文帮你理清思路
When you use AI coding assistants , you eventually run into the same question: "Which tool actually fits me?" GitHub Copilot, Cursor, Claude, Replit —…
8
MatchAttention: Embedding Explicit Matching Constraints into Attention for Efficient Stereo Matching
这篇论文提出MatchAttention注意力机制，将显式匹配约束嵌入到Transformer中，显著提升立体匹配的准确性和效率
arXiv:2510.14260v3 Announce Type: replace Abstract: Standard attention mechanisms are not well suited to stereo matching. Global attention scales quad…
9
Labeling Training Data for Entity Matching Using Large Language Models
研究利用大语言模型自动为实体匹配任务标注训练数据，探索提升标注效率与准确性的新方法。
arXiv:2606.28823v1 Announce Type: new Abstract: Recent large language models (LLMs) achieve strong performance on entity matching without requiring ta…
10
AI 购物匹配精准度仅 16%，上海消保委呼吁电商平台“算法向善”
IT之家 6 月 26 日消息，今日下午，由上海市消费者权益保护委员会、上海市消保基金会主办的“提振消费维护权益”大讲堂在上海开讲。 本次活动以“推动平台算法向善维护消费者合法权益”为主题，聚焦平台算法与消费者权益保护。会上，上海市消保委发布了《2026 年 618 网购体验消费者调查报告》。该报告…
11
Ask HN: How to avoid LLMs struggling with Lisp parens?
LLM生成Lisp代码时总被括号逼疯？看网友分享高招——调整提示方式、分步验证，或改用结构化输出。
LLMs seem to love certain languages (Python, Bash, etc.), but they all seem to struggle with Lisp (e.g. Racket or Emacs Lisp). I've tried various iter…
12
See HN comments that link to specific sites
在Hacker News评论里快速筛选出包含特定网站链接的评论，只需在URL加个参数，还能匹配子域名
To show comments containing links to foo.com, visit /from?site=foo.com&kind=comment. For example, to see all comments containing links to x.com: h…
13
Search Autocomplete Systems — Complete Guide
揭秘Google搜索自动补全系统如何承受每秒千万级请求与100毫秒硬性延迟
Section 1 — Problem Definition An autocomplete system predicts and suggests query completions as a user types, character by character. The goal is to …
14
Equivariant Flow Matching for Symmetry-Breaking Bifurcation Problems
提出等变流匹配新框架，有效模拟对称破缺分岔问题，为物理模拟的机器学习方法注入新思路。
arXiv:2509.03340v4 Announce Type: replace-cross Abstract: Bifurcation phenomena in nonlinear dynamical systems often lead to multiple coexisting stabl…
15
Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning
探讨人类与LLM日常推理中共享的模式匹配机制，挑战“真正推理”与“模式匹配”的二分法
arXiv:2606.13607v1 Announce Type: new Abstract: When large language models (LLMs) fail to generalize or make haphazard errors in reasoning, it is ofte…
16
Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data
揭秘大模型在结构化数据上的“卡壳”瞬间：类别先验锁定如何让上下文学习失效
arXiv:2606.11961v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as conditional generators for structured data, re…
17
When Researchers Say Mental Model/Theory of Mind of AI, What Are They Really Talking About?
揭示AI心理理论研究中的概念混淆：模式匹配不等于真正认知，别再误读“机器有思维”了。
arXiv:2510.02660v2 Announce Type: replace-cross Abstract: When researchers claim AI systems possess ToM or mental models, they are fundamentally discu…
18
Beyond Memorization: Distinguishing Between Pattern-Based and Epistemic Reasoning in LLMs Using Epistemic Puzzles
用认知谜题测试LLM推理能力，揭示模型是真正理解还是仅靠模式匹配
arXiv:2603.21350v2 Announce Type: replace Abstract: Epistemic reasoning requires agents to infer the state of the world from partial observations and …
19
WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI Synthesis
提出分布感知小波流匹配方法，实现更高效的3D脑部MRI合成，兼顾生成质量与计算效率
arXiv:2606.08670v1 Announce Type: new Abstract: Large and demographically balanced datasets are essential for reliable neuroimaging biomarkers. Full-r…
20
FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching
脑龄预测新方法：小波流匹配生成高质量3D脑MRI，解决数据不平衡难题
arXiv:2601.05212v2 Announce Type: replace Abstract: Brain Magnetic Resonance Imaging (MRI) plays a central role in studying neurological development, …